MARINE: Multi-relational Network Embeddings with Relational Proximity and Node Attributes

Ming-Han Feng, Chin-Chi Hsu, Cheng-Te Li, Mi-Yen Yeh, Shou-De Lin

Abstract

Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.
BibTeX
@inproceedings{feng2019marine,
  author = {Ming-Han Feng and Chin-Chi Hsu and Cheng-Te Li and Mi-Yen Yeh and Shou-De Lin},
  title = {{MARINE: Multi-relational Network Embeddings with Relational Proximity and Node Attributes}},
  booktitle = {The Web Conference},
  year = {2019},
  doi = {10.1145/3308558.3313715},
}

Loading related content...

Figure